Optical flow evaluation results |
Statistics:
Average
SD
R2.5
R5.0
R10.0
A90
A95
A99
Error type: endpoint angle interpolation normalized interpolation |
A90 interpolation error |
avg. |
Mequon (Hidden texture) im0 GT im1 |
Schefflera (Hidden texture) im0 GT im1 |
Urban (Synthetic) im0 GT im1 |
Teddy (Stereo) im0 GT im1 |
Backyard (High-speed camera) im0 GT im1 |
Basketball (High-speed camera) im0 GT im1 |
Dumptruck (High-speed camera) im0 GT im1 |
Evergreen (High-speed camera) im0 GT im1 | ||||||||||||||||
rank | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | all | disc | untext | |
PMMST [114] | 7.5 | 3.11 2 | 6.22 3 | 1.73 2 | 4.69 17 | 7.39 13 | 1.73 1 | 4.00 11 | 6.35 4 | 1.41 1 | 6.27 2 | 8.12 3 | 4.24 1 | 11.8 3 | 15.8 4 | 4.20 10 | 5.20 5 | 15.3 3 | 3.27 17 | 4.97 10 | 23.2 9 | 2.00 7 | 9.33 24 | 15.6 11 | 1.91 18 |
MDP-Flow2 [68] | 8.8 | 3.11 2 | 6.35 5 | 1.73 2 | 4.55 8 | 7.35 11 | 1.73 1 | 4.00 11 | 6.35 4 | 1.41 1 | 6.32 4 | 8.12 3 | 4.24 1 | 11.8 3 | 15.8 4 | 4.20 10 | 5.32 25 | 16.6 27 | 3.27 17 | 4.97 10 | 22.9 3 | 2.00 7 | 9.33 24 | 15.6 11 | 1.91 18 |
NN-field [71] | 13.7 | 3.11 2 | 6.98 50 | 1.73 2 | 4.51 2 | 6.78 4 | 1.73 1 | 4.00 11 | 6.35 4 | 1.41 1 | 6.48 35 | 9.26 76 | 4.24 1 | 11.8 3 | 15.9 8 | 4.20 10 | 5.32 25 | 17.0 39 | 3.27 17 | 4.93 4 | 22.9 3 | 2.00 7 | 9.27 11 | 15.6 11 | 1.83 1 |
IROF++ [58] | 15.2 | 3.11 2 | 7.16 74 | 1.73 2 | 4.69 17 | 7.62 17 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.27 2 | 8.10 1 | 4.24 1 | 11.9 9 | 16.1 29 | 4.20 10 | 5.23 9 | 16.2 13 | 3.27 17 | 5.03 56 | 23.7 20 | 2.00 7 | 9.26 8 | 15.8 24 | 1.91 18 |
NNF-Local [87] | 15.2 | 3.11 2 | 6.78 32 | 1.73 2 | 4.51 2 | 6.76 3 | 1.73 1 | 4.00 11 | 6.35 4 | 1.41 1 | 6.45 28 | 9.04 59 | 4.24 1 | 11.9 9 | 15.9 8 | 4.20 10 | 5.35 40 | 17.6 63 | 3.32 34 | 4.93 4 | 23.5 15 | 2.00 7 | 9.26 8 | 15.7 20 | 1.83 1 |
PH-Flow [101] | 16.4 | 3.11 2 | 7.12 66 | 1.73 2 | 4.51 2 | 6.86 5 | 1.73 1 | 4.00 11 | 6.35 4 | 1.41 1 | 6.24 1 | 8.10 1 | 4.24 1 | 11.9 9 | 16.0 21 | 4.20 10 | 5.48 84 | 17.9 72 | 3.16 1 | 4.97 10 | 23.6 19 | 2.00 7 | 9.31 22 | 15.8 24 | 1.91 18 |
SepConv-v1 [127] | 16.9 | 2.38 1 | 5.35 1 | 1.41 1 | 4.43 1 | 7.62 17 | 1.73 1 | 2.38 1 | 4.36 1 | 1.73 120 | 6.40 20 | 8.21 8 | 4.36 101 | 11.8 3 | 15.8 4 | 4.16 2 | 4.69 1 | 14.6 1 | 3.16 1 | 4.80 1 | 21.0 1 | 2.08 98 | 8.76 1 | 14.4 1 | 1.91 18 |
NNF-EAC [103] | 18.9 | 3.27 72 | 6.68 17 | 1.73 2 | 4.80 37 | 7.85 32 | 1.73 1 | 4.00 11 | 6.35 4 | 1.41 1 | 6.40 20 | 8.27 11 | 4.32 86 | 11.9 9 | 15.9 8 | 4.20 10 | 5.23 9 | 15.6 5 | 3.27 17 | 4.97 10 | 23.4 11 | 2.00 7 | 9.42 35 | 15.7 20 | 1.91 18 |
SuperFlow [81] | 20.1 | 3.11 2 | 6.24 4 | 1.73 2 | 5.07 64 | 8.81 64 | 1.83 93 | 4.00 11 | 6.68 15 | 1.41 1 | 6.48 35 | 8.50 23 | 4.24 1 | 11.9 9 | 15.9 8 | 4.24 64 | 5.07 3 | 15.9 8 | 3.16 1 | 4.97 10 | 23.7 20 | 2.00 7 | 9.27 11 | 15.5 9 | 1.91 18 |
Layers++ [37] | 21.0 | 3.11 2 | 6.78 32 | 1.73 2 | 4.51 2 | 6.68 1 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.40 20 | 8.41 17 | 4.24 1 | 12.0 31 | 16.3 64 | 4.20 10 | 5.35 40 | 18.7 105 | 3.32 34 | 4.97 10 | 23.5 15 | 2.00 7 | 9.35 29 | 15.9 35 | 1.91 18 |
nLayers [57] | 21.3 | 3.11 2 | 6.83 43 | 1.73 2 | 4.55 8 | 7.23 8 | 1.73 1 | 3.70 2 | 6.06 3 | 1.41 1 | 6.40 20 | 8.54 26 | 4.24 1 | 12.1 70 | 16.4 85 | 4.20 10 | 5.35 40 | 17.7 65 | 3.32 34 | 4.93 4 | 23.4 11 | 2.00 7 | 9.33 24 | 16.0 43 | 1.83 1 |
DeepFlow [86] | 22.6 | 3.11 2 | 6.40 10 | 1.73 2 | 4.97 51 | 8.66 53 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.56 58 | 8.83 46 | 4.24 1 | 11.9 9 | 15.9 8 | 4.24 64 | 5.20 5 | 15.6 5 | 3.37 103 | 4.97 10 | 22.8 2 | 2.00 7 | 9.20 6 | 15.4 5 | 1.91 18 |
DeepFlow2 [108] | 22.8 | 3.11 2 | 6.45 12 | 1.73 2 | 4.97 51 | 8.76 60 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.56 58 | 8.91 55 | 4.24 1 | 11.9 9 | 15.9 8 | 4.24 64 | 5.16 4 | 15.5 4 | 3.32 34 | 5.00 40 | 23.8 27 | 2.00 7 | 9.29 19 | 15.6 11 | 1.91 18 |
IROF-TV [53] | 22.9 | 3.11 2 | 7.12 66 | 1.73 2 | 4.69 17 | 7.85 32 | 1.73 1 | 4.00 11 | 7.35 82 | 1.41 1 | 6.38 9 | 8.50 23 | 4.24 1 | 12.0 31 | 16.1 29 | 4.24 64 | 5.26 13 | 17.1 45 | 3.16 1 | 5.00 40 | 24.1 38 | 2.00 7 | 9.27 11 | 15.4 5 | 1.91 18 |
ProbFlowFields [128] | 23.2 | 3.11 2 | 6.88 45 | 1.73 2 | 4.55 8 | 7.44 14 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.45 28 | 8.70 34 | 4.24 1 | 12.0 31 | 16.4 85 | 4.24 64 | 5.45 60 | 18.0 77 | 3.32 34 | 4.93 4 | 23.1 6 | 1.91 1 | 9.13 3 | 15.6 11 | 1.91 18 |
Brox et al. [5] | 24.3 | 3.11 2 | 6.66 16 | 1.73 2 | 5.07 64 | 8.58 50 | 1.73 1 | 4.00 11 | 7.35 82 | 1.41 1 | 6.56 58 | 8.70 34 | 4.24 1 | 11.9 9 | 15.9 8 | 4.20 10 | 5.32 25 | 17.1 45 | 3.27 17 | 5.00 40 | 24.5 52 | 2.00 7 | 9.29 19 | 15.6 11 | 1.91 18 |
CombBMOF [113] | 24.6 | 3.11 2 | 6.95 48 | 1.73 2 | 4.69 17 | 7.62 17 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.56 58 | 9.09 63 | 4.24 1 | 12.0 31 | 16.1 29 | 4.20 10 | 5.35 40 | 16.4 21 | 3.27 17 | 5.60 123 | 24.3 43 | 2.00 7 | 9.26 8 | 15.8 24 | 1.83 1 |
WLIF-Flow [93] | 24.7 | 3.11 2 | 6.88 45 | 1.73 2 | 4.69 17 | 7.77 27 | 1.73 1 | 4.00 11 | 6.56 13 | 1.41 1 | 6.38 9 | 8.19 5 | 4.32 86 | 11.9 9 | 16.1 29 | 4.20 10 | 5.51 86 | 18.0 77 | 3.32 34 | 4.97 10 | 23.4 11 | 2.00 7 | 9.43 48 | 15.9 35 | 1.91 18 |
LME [70] | 25.1 | 3.11 2 | 6.81 39 | 1.73 2 | 4.76 34 | 7.94 37 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.38 9 | 8.50 23 | 4.24 1 | 12.1 70 | 16.3 64 | 4.24 64 | 5.42 58 | 17.0 39 | 3.27 17 | 4.97 10 | 23.0 5 | 2.00 7 | 9.29 19 | 15.8 24 | 1.91 18 |
DF-Auto [115] | 25.1 | 3.11 2 | 6.06 2 | 1.73 2 | 5.07 64 | 8.58 50 | 1.83 93 | 4.00 11 | 6.35 4 | 1.41 1 | 6.48 35 | 8.58 29 | 4.24 1 | 11.7 2 | 15.7 2 | 4.24 64 | 5.20 5 | 16.1 11 | 3.32 34 | 5.07 63 | 23.8 27 | 2.00 7 | 9.45 52 | 15.8 24 | 1.91 18 |
Aniso. Huber-L1 [22] | 26.0 | 3.27 72 | 6.78 32 | 1.73 2 | 5.45 88 | 9.66 87 | 1.73 1 | 4.00 11 | 6.73 39 | 1.41 1 | 6.48 35 | 8.81 43 | 4.24 1 | 11.9 9 | 15.9 8 | 4.20 10 | 5.26 13 | 16.3 16 | 3.16 1 | 5.07 63 | 23.9 30 | 2.00 7 | 9.38 31 | 15.4 5 | 1.91 18 |
COFM [59] | 26.0 | 3.11 2 | 6.76 31 | 1.73 2 | 4.69 17 | 7.62 17 | 1.73 1 | 4.00 11 | 6.66 14 | 1.41 1 | 6.35 5 | 8.35 13 | 4.24 1 | 12.0 31 | 16.2 46 | 4.16 2 | 5.45 60 | 18.9 108 | 3.16 1 | 4.80 1 | 23.1 6 | 2.08 98 | 9.56 72 | 16.3 65 | 1.91 18 |
TV-L1-MCT [64] | 26.0 | 3.37 96 | 7.62 108 | 1.73 2 | 4.83 39 | 8.58 50 | 1.73 1 | 3.70 2 | 6.68 15 | 1.41 1 | 6.38 9 | 8.25 10 | 4.24 1 | 12.1 70 | 16.4 85 | 4.20 10 | 5.20 5 | 16.0 9 | 3.32 34 | 4.97 10 | 24.0 34 | 2.00 7 | 9.15 4 | 15.4 5 | 1.91 18 |
FlowFields [110] | 26.5 | 3.11 2 | 7.14 69 | 1.73 2 | 4.69 17 | 7.79 29 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.48 35 | 9.35 81 | 4.24 1 | 12.0 31 | 16.2 46 | 4.20 10 | 5.45 60 | 17.6 63 | 3.32 34 | 4.97 10 | 23.5 15 | 2.00 7 | 9.27 11 | 15.9 35 | 1.91 18 |
Sparse-NonSparse [56] | 26.7 | 3.11 2 | 7.07 62 | 1.73 2 | 4.65 12 | 7.53 16 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.38 9 | 8.37 16 | 4.24 1 | 12.0 31 | 16.3 64 | 4.20 10 | 5.45 60 | 18.1 83 | 3.32 34 | 4.97 10 | 25.4 78 | 2.00 7 | 9.42 35 | 16.2 62 | 1.91 18 |
FMOF [94] | 26.9 | 3.32 78 | 7.39 90 | 1.73 2 | 4.65 12 | 7.35 11 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.53 56 | 8.98 57 | 4.24 1 | 12.0 31 | 16.1 29 | 4.20 10 | 5.35 40 | 17.0 39 | 3.27 17 | 4.93 4 | 23.5 15 | 1.91 1 | 9.47 53 | 16.1 53 | 1.91 18 |
ComponentFusion [96] | 27.2 | 3.11 2 | 7.16 74 | 1.73 2 | 4.69 17 | 7.72 23 | 1.73 1 | 4.00 11 | 6.88 46 | 1.41 1 | 6.38 9 | 8.54 26 | 4.24 1 | 12.0 31 | 16.2 46 | 4.20 10 | 5.26 13 | 16.8 30 | 3.32 34 | 5.03 56 | 26.3 97 | 2.00 7 | 9.42 35 | 16.2 62 | 1.91 18 |
TF+OM [100] | 27.9 | 3.11 2 | 6.48 13 | 1.73 2 | 4.69 17 | 7.75 26 | 1.73 1 | 4.00 11 | 7.33 81 | 1.41 1 | 6.48 35 | 9.09 63 | 4.24 1 | 12.0 31 | 16.2 46 | 4.24 64 | 5.26 13 | 17.2 51 | 3.32 34 | 4.97 10 | 24.8 59 | 2.00 7 | 9.43 48 | 15.9 35 | 1.91 18 |
2DHMM-SAS [92] | 29.8 | 3.27 72 | 7.48 98 | 1.73 2 | 5.07 64 | 8.96 67 | 1.73 1 | 3.70 2 | 6.68 15 | 1.41 1 | 6.35 5 | 8.19 5 | 4.24 1 | 12.0 31 | 16.2 46 | 4.20 10 | 5.32 25 | 17.0 39 | 3.27 17 | 4.97 10 | 24.4 50 | 2.00 7 | 9.49 63 | 16.3 65 | 1.91 18 |
Second-order prior [8] | 29.9 | 3.11 2 | 6.63 15 | 1.73 2 | 5.32 79 | 9.63 85 | 1.73 1 | 4.00 11 | 7.68 100 | 1.41 1 | 6.56 58 | 9.11 67 | 4.24 1 | 11.9 9 | 16.0 21 | 4.20 10 | 5.23 9 | 16.4 21 | 3.27 17 | 5.10 77 | 24.4 50 | 2.00 7 | 9.40 33 | 15.8 24 | 1.91 18 |
PGM-C [120] | 30.7 | 3.11 2 | 7.05 57 | 1.73 2 | 4.69 17 | 7.83 31 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.48 35 | 9.42 83 | 4.24 1 | 12.0 31 | 16.2 46 | 4.24 64 | 5.32 25 | 16.9 33 | 3.32 34 | 5.00 40 | 25.0 66 | 2.00 7 | 9.33 24 | 16.0 43 | 1.91 18 |
CLG-TV [48] | 31.0 | 3.16 59 | 6.61 14 | 1.73 2 | 5.35 81 | 9.56 81 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.56 58 | 8.81 43 | 4.24 1 | 11.9 9 | 15.9 8 | 4.24 64 | 5.26 13 | 16.0 9 | 3.32 34 | 5.07 63 | 24.3 43 | 2.00 7 | 9.43 48 | 15.6 11 | 1.91 18 |
CPM-Flow [116] | 31.2 | 3.11 2 | 7.05 57 | 1.73 2 | 4.69 17 | 7.85 32 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.56 58 | 9.81 99 | 4.24 1 | 12.0 31 | 16.3 64 | 4.24 64 | 5.29 23 | 16.5 23 | 3.32 34 | 5.07 63 | 24.7 58 | 2.00 7 | 9.27 11 | 15.8 24 | 1.91 18 |
FlowFields+ [130] | 31.2 | 3.11 2 | 7.23 82 | 1.73 2 | 4.69 17 | 7.72 23 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.45 28 | 9.33 79 | 4.24 1 | 12.1 70 | 16.3 64 | 4.24 64 | 5.45 60 | 17.9 72 | 3.32 34 | 4.97 10 | 23.7 20 | 2.00 7 | 9.27 11 | 16.0 43 | 1.83 1 |
ALD-Flow [66] | 31.6 | 3.16 59 | 6.98 50 | 1.73 2 | 4.83 39 | 8.54 49 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.40 20 | 8.54 26 | 4.24 1 | 12.1 70 | 16.2 46 | 4.24 64 | 5.32 25 | 15.8 7 | 3.32 34 | 4.97 10 | 23.1 6 | 2.00 7 | 9.54 70 | 16.4 78 | 1.91 18 |
MDP-Flow [26] | 31.7 | 3.11 2 | 6.68 17 | 1.73 2 | 4.65 12 | 7.44 14 | 1.73 1 | 4.00 11 | 6.35 4 | 1.41 1 | 6.58 77 | 8.96 56 | 4.24 1 | 11.9 9 | 16.1 29 | 4.24 64 | 5.60 94 | 19.2 112 | 3.32 34 | 5.16 86 | 24.3 43 | 2.00 7 | 9.33 24 | 16.0 43 | 1.91 18 |
HAST [109] | 32.4 | 3.11 2 | 6.68 17 | 1.73 2 | 4.65 12 | 7.33 9 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.35 5 | 8.23 9 | 4.24 1 | 12.1 70 | 16.5 102 | 4.20 10 | 5.45 60 | 19.9 118 | 3.16 1 | 4.90 3 | 25.2 72 | 2.00 7 | 9.81 97 | 16.9 103 | 1.91 18 |
DPOF [18] | 32.7 | 3.16 59 | 7.55 104 | 1.73 2 | 4.55 8 | 7.05 7 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.56 58 | 9.20 74 | 4.24 1 | 11.9 9 | 16.0 21 | 4.20 10 | 5.45 60 | 17.8 69 | 3.16 1 | 5.10 77 | 24.0 34 | 2.00 7 | 9.56 72 | 16.3 65 | 1.91 18 |
F-TV-L1 [15] | 32.8 | 3.37 96 | 6.68 17 | 1.73 2 | 5.48 92 | 9.76 94 | 1.73 1 | 4.00 11 | 7.35 82 | 1.41 1 | 6.56 58 | 8.76 41 | 4.32 86 | 11.8 3 | 15.8 4 | 4.16 2 | 5.26 13 | 16.1 11 | 3.32 34 | 5.00 40 | 24.0 34 | 2.00 7 | 9.35 29 | 15.6 11 | 1.91 18 |
LSM [39] | 32.8 | 3.11 2 | 7.53 100 | 1.73 2 | 4.69 17 | 7.79 29 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.45 28 | 8.70 34 | 4.24 1 | 12.0 31 | 16.3 64 | 4.20 10 | 5.45 60 | 18.3 87 | 3.32 34 | 4.97 10 | 25.5 79 | 2.00 7 | 9.47 53 | 16.4 78 | 1.83 1 |
Classic+NL [31] | 33.3 | 3.27 72 | 7.35 85 | 1.73 2 | 4.69 17 | 7.68 22 | 1.73 1 | 3.70 2 | 6.68 15 | 1.41 1 | 6.38 9 | 8.35 13 | 4.24 1 | 12.0 31 | 16.3 64 | 4.20 10 | 5.48 84 | 18.1 83 | 3.32 34 | 4.97 10 | 25.8 86 | 2.00 7 | 9.52 68 | 16.3 65 | 1.91 18 |
Ramp [62] | 34.4 | 3.16 59 | 7.19 78 | 1.73 2 | 4.69 17 | 7.62 17 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.35 5 | 8.27 11 | 4.24 1 | 12.0 31 | 16.3 64 | 4.20 10 | 5.51 86 | 18.9 108 | 3.32 34 | 4.97 10 | 25.9 90 | 2.00 7 | 9.56 72 | 16.4 78 | 1.91 18 |
AGIF+OF [85] | 34.4 | 3.11 2 | 7.39 90 | 1.73 2 | 4.69 17 | 7.77 27 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.38 9 | 8.45 21 | 4.24 1 | 12.2 102 | 16.6 109 | 4.20 10 | 5.51 86 | 18.5 96 | 3.27 17 | 4.97 10 | 23.7 20 | 1.91 1 | 9.59 83 | 16.6 94 | 1.83 1 |
RFlow [90] | 34.6 | 3.11 2 | 6.81 39 | 1.73 2 | 5.32 79 | 9.80 96 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.58 77 | 9.26 76 | 4.24 1 | 11.9 9 | 16.0 21 | 4.20 10 | 5.26 13 | 17.1 45 | 3.16 1 | 5.03 56 | 24.9 64 | 2.00 7 | 9.61 85 | 16.1 53 | 1.91 18 |
S2F-IF [123] | 34.6 | 3.11 2 | 7.19 78 | 1.73 2 | 4.69 17 | 7.72 23 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.48 35 | 9.35 81 | 4.24 1 | 12.1 70 | 16.4 85 | 4.24 64 | 5.45 60 | 17.8 69 | 3.32 34 | 5.00 40 | 24.1 38 | 2.00 7 | 9.27 11 | 16.1 53 | 1.83 1 |
CBF [12] | 35.0 | 3.11 2 | 6.38 8 | 1.73 2 | 5.07 64 | 8.72 56 | 1.73 1 | 4.00 11 | 6.73 39 | 1.41 1 | 6.56 58 | 8.60 32 | 4.43 107 | 11.9 9 | 15.9 8 | 4.24 64 | 5.32 25 | 16.5 23 | 3.27 17 | 5.07 63 | 24.5 52 | 2.08 98 | 9.49 63 | 15.7 20 | 1.91 18 |
LDOF [28] | 35.3 | 3.37 96 | 6.68 17 | 1.73 2 | 5.35 81 | 8.35 40 | 1.83 93 | 4.00 11 | 7.35 82 | 1.41 1 | 6.61 83 | 9.09 63 | 4.24 1 | 11.9 9 | 15.9 8 | 4.24 64 | 5.23 9 | 16.2 13 | 3.32 34 | 5.00 40 | 23.7 20 | 2.00 7 | 9.38 31 | 15.8 24 | 1.91 18 |
OAR-Flow [125] | 35.8 | 3.11 2 | 6.95 48 | 1.73 2 | 4.97 51 | 8.68 54 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.38 9 | 8.58 29 | 4.24 1 | 12.1 70 | 16.3 64 | 4.24 64 | 5.45 60 | 16.9 33 | 3.32 34 | 5.07 63 | 25.3 73 | 2.00 7 | 9.47 53 | 16.3 65 | 1.91 18 |
p-harmonic [29] | 36.2 | 3.11 2 | 6.68 17 | 1.73 2 | 5.45 88 | 9.68 89 | 1.73 1 | 4.00 11 | 7.39 99 | 1.41 1 | 6.68 87 | 9.15 72 | 4.24 1 | 12.0 31 | 16.1 29 | 4.20 10 | 5.32 25 | 16.5 23 | 3.32 34 | 5.20 90 | 24.8 59 | 2.00 7 | 9.43 48 | 15.8 24 | 1.91 18 |
RNLOD-Flow [121] | 37.2 | 3.11 2 | 7.07 62 | 1.73 2 | 4.97 51 | 8.81 64 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.45 28 | 8.66 33 | 4.24 1 | 12.1 70 | 16.4 85 | 4.20 10 | 5.45 60 | 18.3 87 | 3.32 34 | 4.97 10 | 23.9 30 | 2.00 7 | 9.81 97 | 16.8 98 | 1.83 1 |
ComplOF-FED-GPU [35] | 37.2 | 3.11 2 | 7.05 57 | 1.73 2 | 4.83 39 | 8.43 42 | 1.73 1 | 4.08 94 | 7.19 79 | 1.41 1 | 6.48 35 | 9.11 67 | 4.24 1 | 12.0 31 | 16.1 29 | 4.20 10 | 5.35 40 | 17.1 45 | 3.32 34 | 5.07 63 | 24.8 59 | 2.00 7 | 9.56 72 | 16.3 65 | 1.91 18 |
Kuang [131] | 37.3 | 3.11 2 | 7.33 84 | 1.73 2 | 4.83 39 | 8.25 39 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.48 35 | 9.45 89 | 4.24 1 | 12.1 70 | 16.3 64 | 4.24 64 | 5.35 40 | 17.2 51 | 3.27 17 | 5.10 77 | 25.3 73 | 2.00 7 | 9.27 11 | 15.9 35 | 1.91 18 |
SIOF [67] | 37.7 | 3.37 96 | 6.98 50 | 1.73 2 | 5.48 92 | 10.0 104 | 1.83 93 | 4.00 11 | 7.00 47 | 1.41 1 | 6.48 35 | 8.76 41 | 4.24 1 | 11.8 3 | 15.7 2 | 4.20 10 | 5.32 25 | 16.2 13 | 3.32 34 | 5.07 63 | 23.7 20 | 2.00 7 | 9.59 83 | 16.1 53 | 1.91 18 |
TC-Flow [46] | 37.7 | 3.11 2 | 6.81 39 | 1.73 2 | 4.90 44 | 8.76 60 | 1.73 1 | 4.00 11 | 7.35 82 | 1.41 1 | 6.45 28 | 8.81 43 | 4.24 1 | 12.1 70 | 16.4 85 | 4.24 64 | 5.45 60 | 17.0 39 | 3.32 34 | 5.00 40 | 24.3 43 | 2.00 7 | 9.47 53 | 16.4 78 | 1.91 18 |
FC-2Layers-FF [74] | 38.2 | 3.16 59 | 7.23 82 | 1.73 2 | 4.51 2 | 6.68 1 | 1.73 1 | 4.00 11 | 6.78 43 | 1.41 1 | 6.40 20 | 8.49 22 | 4.24 1 | 12.1 70 | 16.4 85 | 4.20 10 | 5.57 90 | 19.0 111 | 3.32 34 | 4.97 10 | 25.6 81 | 2.00 7 | 9.57 79 | 16.4 78 | 1.91 18 |
EpicFlow [102] | 40.5 | 3.11 2 | 7.07 62 | 1.73 2 | 4.90 44 | 8.74 58 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.56 58 | 9.59 97 | 4.24 1 | 12.0 31 | 16.3 64 | 4.24 64 | 5.35 40 | 17.4 57 | 3.27 17 | 5.07 63 | 25.7 85 | 2.00 7 | 9.42 35 | 16.5 89 | 1.91 18 |
Local-TV-L1 [65] | 41.2 | 3.32 78 | 6.35 5 | 1.83 104 | 5.51 97 | 9.63 85 | 1.83 93 | 4.00 11 | 6.68 15 | 1.41 1 | 6.48 35 | 8.70 34 | 4.55 114 | 11.9 9 | 16.0 21 | 4.24 64 | 5.32 25 | 16.3 16 | 3.51 125 | 4.97 10 | 23.4 11 | 2.00 7 | 9.20 6 | 15.3 4 | 1.91 18 |
OFLAF [77] | 41.2 | 3.11 2 | 6.98 50 | 1.73 2 | 4.51 2 | 7.00 6 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.40 20 | 8.43 19 | 4.24 1 | 12.1 70 | 16.4 85 | 4.24 64 | 5.60 94 | 18.7 105 | 3.32 34 | 5.07 63 | 28.0 113 | 2.00 7 | 9.83 101 | 17.0 106 | 1.91 18 |
S2D-Matching [84] | 41.6 | 3.32 78 | 7.37 89 | 1.73 2 | 5.00 61 | 9.00 68 | 1.73 1 | 3.70 2 | 6.68 15 | 1.41 1 | 6.38 9 | 8.35 13 | 4.24 1 | 12.1 70 | 16.5 102 | 4.20 10 | 5.57 90 | 18.8 107 | 3.32 34 | 5.00 40 | 24.5 52 | 2.00 7 | 9.49 63 | 16.3 65 | 1.91 18 |
Classic++ [32] | 43.3 | 3.11 2 | 6.78 32 | 1.73 2 | 5.07 64 | 9.15 72 | 1.73 1 | 4.00 11 | 7.12 75 | 1.41 1 | 6.56 58 | 8.83 46 | 4.32 86 | 12.0 31 | 16.2 46 | 4.24 64 | 5.45 60 | 17.7 65 | 3.37 103 | 5.00 40 | 24.8 59 | 2.00 7 | 9.47 53 | 16.0 43 | 1.91 18 |
AggregFlow [97] | 43.3 | 3.32 78 | 7.85 113 | 1.73 2 | 4.97 51 | 8.76 60 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.61 83 | 9.81 99 | 4.24 1 | 12.0 31 | 16.2 46 | 4.24 64 | 5.32 25 | 16.5 23 | 3.37 103 | 4.97 10 | 25.0 66 | 2.00 7 | 9.47 53 | 16.4 78 | 1.91 18 |
Modified CLG [34] | 43.5 | 3.11 2 | 6.40 10 | 1.73 2 | 5.80 107 | 9.75 93 | 2.00 114 | 4.00 11 | 7.77 106 | 1.41 1 | 6.68 87 | 9.43 87 | 4.24 1 | 12.0 31 | 16.1 29 | 4.24 64 | 5.35 40 | 16.9 33 | 3.32 34 | 5.10 77 | 23.9 30 | 2.00 7 | 9.42 35 | 15.8 24 | 1.91 18 |
FlowNetS+ft+v [112] | 44.3 | 3.32 78 | 6.68 17 | 1.73 2 | 5.69 102 | 9.76 94 | 1.83 93 | 4.00 11 | 7.35 82 | 1.41 1 | 6.58 77 | 9.13 71 | 4.24 1 | 12.0 31 | 16.1 29 | 4.24 64 | 5.26 13 | 16.3 16 | 3.32 34 | 5.07 63 | 25.9 90 | 2.00 7 | 9.42 35 | 15.9 35 | 1.91 18 |
TC/T-Flow [76] | 45.0 | 3.32 78 | 7.53 100 | 1.73 2 | 4.93 47 | 8.74 58 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.48 35 | 8.87 51 | 4.24 1 | 12.1 70 | 16.4 85 | 4.24 64 | 5.45 60 | 16.8 30 | 3.32 34 | 5.10 77 | 26.6 99 | 2.00 7 | 9.63 87 | 16.3 65 | 1.83 1 |
SVFilterOh [111] | 46.2 | 3.16 59 | 6.73 27 | 1.73 2 | 4.65 12 | 7.33 9 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.48 35 | 8.74 39 | 4.36 101 | 12.2 102 | 16.5 102 | 4.24 64 | 5.45 60 | 18.6 99 | 3.32 34 | 4.93 4 | 23.9 30 | 2.08 98 | 9.70 92 | 16.7 95 | 1.91 18 |
CRTflow [80] | 46.5 | 3.32 78 | 7.05 57 | 1.73 2 | 5.26 77 | 9.54 80 | 1.73 1 | 4.36 105 | 7.85 108 | 1.41 1 | 6.48 35 | 8.74 39 | 4.40 105 | 12.0 31 | 16.2 46 | 4.24 64 | 5.32 25 | 16.3 16 | 3.32 34 | 5.00 40 | 25.1 70 | 2.00 7 | 9.42 35 | 16.0 43 | 1.91 18 |
OFH [38] | 46.8 | 3.16 59 | 7.14 69 | 1.73 2 | 5.10 72 | 9.15 72 | 1.73 1 | 4.00 11 | 7.79 107 | 1.41 1 | 6.45 28 | 9.04 59 | 4.24 1 | 12.0 31 | 16.3 64 | 4.20 10 | 5.45 60 | 17.3 55 | 3.32 34 | 5.10 77 | 27.1 107 | 2.00 7 | 9.57 79 | 16.8 98 | 1.91 18 |
PMF [73] | 47.3 | 3.11 2 | 7.14 69 | 1.73 2 | 4.97 51 | 8.49 46 | 1.73 1 | 4.00 11 | 8.00 110 | 1.41 1 | 6.48 35 | 8.89 52 | 4.24 1 | 12.2 102 | 16.5 102 | 4.20 10 | 5.45 60 | 17.4 57 | 3.37 103 | 4.97 10 | 25.5 79 | 2.00 7 | 9.90 109 | 17.3 115 | 1.83 1 |
Steered-L1 [118] | 47.5 | 3.11 2 | 6.78 32 | 1.73 2 | 4.93 47 | 8.52 48 | 1.73 1 | 4.08 94 | 7.00 47 | 1.41 1 | 6.68 87 | 9.06 62 | 4.43 107 | 12.1 70 | 16.4 85 | 4.20 10 | 5.35 40 | 17.4 57 | 3.32 34 | 5.00 40 | 25.6 81 | 2.00 7 | 9.68 89 | 16.4 78 | 1.91 18 |
Efficient-NL [60] | 47.7 | 3.32 78 | 7.19 78 | 1.73 2 | 4.90 44 | 8.50 47 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.56 58 | 8.83 46 | 4.24 1 | 12.0 31 | 16.3 64 | 4.20 10 | 5.80 108 | 18.9 108 | 3.16 1 | 5.07 63 | 26.6 99 | 2.00 7 | 9.97 116 | 17.0 106 | 1.91 18 |
EPPM w/o HM [88] | 47.8 | 3.11 2 | 7.77 112 | 1.73 2 | 4.97 51 | 8.76 60 | 1.73 1 | 4.08 94 | 8.39 117 | 1.41 1 | 6.48 35 | 9.42 83 | 4.24 1 | 12.0 31 | 16.2 46 | 4.20 10 | 5.45 60 | 18.3 87 | 3.32 34 | 5.16 86 | 25.0 66 | 2.00 7 | 9.56 72 | 16.5 89 | 1.83 1 |
BlockOverlap [61] | 48.4 | 3.32 78 | 6.35 5 | 1.83 104 | 5.48 92 | 9.33 77 | 1.91 108 | 4.00 11 | 6.35 4 | 1.41 1 | 6.48 35 | 8.19 5 | 4.65 119 | 12.0 31 | 16.1 29 | 4.36 124 | 5.35 40 | 16.6 27 | 3.42 118 | 4.97 10 | 23.7 20 | 2.08 98 | 9.15 4 | 15.1 3 | 1.91 18 |
Adaptive [20] | 49.5 | 3.32 78 | 6.83 43 | 1.73 2 | 5.69 102 | 10.4 115 | 1.73 1 | 4.00 11 | 7.35 82 | 1.41 1 | 6.53 56 | 8.89 52 | 4.24 1 | 12.0 31 | 16.2 46 | 4.20 10 | 5.45 60 | 17.9 72 | 3.32 34 | 5.20 90 | 27.4 111 | 2.00 7 | 9.63 87 | 16.4 78 | 1.91 18 |
FESL [72] | 49.5 | 3.32 78 | 7.39 90 | 1.73 2 | 4.76 34 | 7.87 35 | 1.73 1 | 4.00 11 | 7.00 47 | 1.41 1 | 6.56 58 | 8.89 52 | 4.24 1 | 12.1 70 | 16.5 102 | 4.24 64 | 5.72 99 | 18.6 99 | 3.32 34 | 5.00 40 | 25.6 81 | 1.91 1 | 9.68 89 | 16.8 98 | 1.83 1 |
Sparse Occlusion [54] | 49.8 | 3.27 72 | 7.05 57 | 1.73 2 | 5.07 64 | 9.56 81 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.58 77 | 9.04 59 | 4.24 1 | 12.1 70 | 16.3 64 | 4.24 64 | 5.69 97 | 18.6 99 | 3.32 34 | 5.07 63 | 26.2 94 | 1.91 1 | 9.61 85 | 16.3 65 | 1.91 18 |
TCOF [69] | 50.0 | 3.32 78 | 7.14 69 | 1.73 2 | 5.72 104 | 10.3 111 | 1.73 1 | 4.00 11 | 6.78 43 | 1.41 1 | 6.56 58 | 8.83 46 | 4.24 1 | 12.0 31 | 16.0 21 | 4.20 10 | 5.72 99 | 18.0 77 | 3.16 1 | 5.35 110 | 27.1 107 | 2.00 7 | 9.87 104 | 16.5 89 | 1.91 18 |
TV-L1-improved [17] | 50.7 | 3.16 59 | 6.73 27 | 1.73 2 | 5.60 98 | 10.2 107 | 1.73 1 | 4.08 94 | 7.05 64 | 1.41 1 | 6.58 77 | 9.02 58 | 4.24 1 | 12.0 31 | 16.2 46 | 4.20 10 | 5.45 60 | 18.4 93 | 3.32 34 | 5.20 90 | 28.7 116 | 2.00 7 | 9.54 70 | 16.1 53 | 1.91 18 |
MLDP_OF [89] | 50.7 | 3.11 2 | 7.35 85 | 1.73 2 | 4.97 51 | 8.87 66 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.48 35 | 8.58 29 | 4.32 86 | 12.0 31 | 16.2 46 | 4.24 64 | 5.80 108 | 18.5 96 | 3.46 123 | 5.20 90 | 24.2 41 | 2.08 98 | 9.47 53 | 16.3 65 | 1.91 18 |
Complementary OF [21] | 50.8 | 3.11 2 | 7.35 85 | 1.73 2 | 4.83 39 | 8.43 42 | 1.73 1 | 4.36 105 | 7.05 64 | 1.41 1 | 6.48 35 | 9.15 72 | 4.24 1 | 12.1 70 | 16.4 85 | 4.20 10 | 5.42 58 | 17.8 69 | 3.32 34 | 5.16 86 | 27.0 106 | 2.00 7 | 9.87 104 | 18.1 122 | 1.91 18 |
CNN-flow-warp+ref [117] | 51.0 | 3.11 2 | 6.38 8 | 1.73 2 | 5.35 81 | 9.42 78 | 1.73 1 | 4.36 105 | 7.94 109 | 1.41 1 | 7.19 113 | 9.88 102 | 4.51 111 | 12.0 31 | 16.1 29 | 4.24 64 | 5.29 23 | 16.8 30 | 3.32 34 | 5.20 90 | 27.3 109 | 2.00 7 | 9.40 33 | 16.0 43 | 1.91 18 |
Classic+CPF [83] | 51.5 | 3.16 59 | 7.44 96 | 1.73 2 | 4.76 34 | 8.04 38 | 1.73 1 | 3.70 2 | 6.73 39 | 1.41 1 | 6.40 20 | 8.43 19 | 4.24 1 | 12.3 116 | 16.8 119 | 4.24 64 | 5.74 106 | 19.2 112 | 3.32 34 | 5.07 63 | 25.9 90 | 1.91 1 | 9.88 106 | 17.1 112 | 1.83 1 |
SRR-TVOF-NL [91] | 51.5 | 3.32 78 | 7.53 100 | 1.73 2 | 5.10 72 | 9.15 72 | 1.73 1 | 4.00 11 | 7.05 64 | 1.41 1 | 6.68 87 | 9.33 79 | 4.24 1 | 12.1 70 | 16.4 85 | 4.20 10 | 5.35 40 | 17.9 72 | 3.16 1 | 5.23 100 | 24.3 43 | 2.00 7 | 9.97 116 | 17.0 106 | 1.91 18 |
Fusion [6] | 51.6 | 3.11 2 | 7.12 66 | 1.73 2 | 4.80 37 | 7.90 36 | 1.73 1 | 4.00 11 | 6.73 39 | 1.41 1 | 6.83 98 | 9.26 76 | 4.24 1 | 12.2 102 | 16.5 102 | 4.16 2 | 5.80 108 | 19.6 115 | 3.16 1 | 5.20 90 | 25.9 90 | 2.00 7 | 10.2 119 | 17.3 115 | 1.91 18 |
Occlusion-TV-L1 [63] | 53.0 | 3.27 72 | 6.81 39 | 1.73 2 | 5.45 88 | 10.2 107 | 1.73 1 | 4.00 11 | 7.35 82 | 1.41 1 | 6.66 86 | 9.43 87 | 4.32 86 | 11.9 9 | 15.9 8 | 4.24 64 | 5.35 40 | 17.2 51 | 3.37 103 | 5.32 105 | 24.3 43 | 2.08 98 | 9.42 35 | 15.9 35 | 1.91 18 |
CostFilter [40] | 54.0 | 3.11 2 | 7.90 114 | 1.73 2 | 4.93 47 | 8.43 42 | 1.73 1 | 4.00 11 | 8.68 119 | 1.41 1 | 6.56 58 | 9.68 98 | 4.24 1 | 12.2 102 | 16.7 114 | 4.20 10 | 5.45 60 | 17.0 39 | 3.46 123 | 5.00 40 | 26.2 94 | 2.00 7 | 9.80 96 | 17.3 115 | 1.83 1 |
BriefMatch [124] | 54.7 | 3.11 2 | 7.19 78 | 1.73 2 | 4.97 51 | 8.43 42 | 1.73 1 | 4.36 105 | 7.00 47 | 1.41 1 | 6.98 102 | 9.42 83 | 4.69 123 | 12.1 70 | 16.2 46 | 4.24 64 | 5.72 99 | 18.5 96 | 3.70 128 | 4.97 10 | 24.2 41 | 2.00 7 | 9.42 35 | 16.2 62 | 1.91 18 |
2D-CLG [1] | 55.9 | 3.16 59 | 6.73 27 | 1.83 104 | 6.16 114 | 9.88 102 | 2.16 120 | 4.08 94 | 7.35 82 | 1.41 1 | 7.05 107 | 9.95 104 | 4.24 1 | 11.9 9 | 16.0 21 | 4.20 10 | 5.35 40 | 16.9 33 | 3.32 34 | 5.23 100 | 26.6 99 | 2.00 7 | 9.42 35 | 15.7 20 | 1.91 18 |
HBM-GC [105] | 56.5 | 3.32 78 | 7.16 74 | 1.73 2 | 4.93 47 | 8.72 56 | 1.73 1 | 3.74 10 | 6.00 2 | 1.41 1 | 6.48 35 | 8.70 34 | 4.32 86 | 12.3 116 | 16.7 114 | 4.32 122 | 5.80 108 | 20.9 126 | 3.32 34 | 4.97 10 | 24.5 52 | 2.08 98 | 9.57 79 | 16.1 53 | 1.91 18 |
SimpleFlow [49] | 57.5 | 3.16 59 | 7.42 93 | 1.73 2 | 5.07 64 | 9.00 68 | 1.73 1 | 4.00 11 | 7.14 77 | 1.41 1 | 6.38 9 | 8.41 17 | 4.24 1 | 12.1 70 | 16.5 102 | 4.20 10 | 5.72 99 | 19.6 115 | 3.32 34 | 5.16 86 | 32.0 128 | 2.08 98 | 9.81 97 | 17.6 119 | 1.91 18 |
IAOF [50] | 57.5 | 3.42 108 | 7.16 74 | 1.83 104 | 6.88 125 | 11.7 130 | 1.91 108 | 3.70 2 | 7.35 82 | 1.41 1 | 6.98 102 | 9.49 93 | 4.24 1 | 11.9 9 | 16.0 21 | 4.20 10 | 5.32 25 | 17.2 51 | 3.32 34 | 5.20 90 | 25.1 70 | 2.00 7 | 9.56 72 | 16.0 43 | 1.91 18 |
Nguyen [33] | 58.5 | 3.37 96 | 6.78 32 | 1.91 117 | 6.56 123 | 10.5 119 | 2.00 114 | 4.00 11 | 8.00 110 | 1.41 1 | 7.14 111 | 10.3 111 | 4.24 1 | 11.9 9 | 16.1 29 | 4.20 10 | 5.32 25 | 17.1 45 | 3.16 1 | 5.72 127 | 28.7 116 | 2.00 7 | 9.42 35 | 15.9 35 | 1.91 18 |
TriFlow [95] | 58.9 | 3.16 59 | 7.42 93 | 1.73 2 | 5.35 81 | 9.68 89 | 1.83 93 | 4.00 11 | 7.35 82 | 1.41 1 | 6.58 77 | 9.45 89 | 4.24 1 | 12.2 102 | 16.6 109 | 4.24 64 | 5.45 60 | 18.0 77 | 3.32 34 | 5.00 40 | 24.6 56 | 2.00 7 | 9.57 79 | 16.5 89 | 1.91 18 |
Rannacher [23] | 58.9 | 3.32 78 | 7.00 56 | 1.73 2 | 5.60 98 | 10.4 115 | 1.73 1 | 4.08 94 | 7.35 82 | 1.41 1 | 6.56 58 | 9.11 67 | 4.32 86 | 12.0 31 | 16.1 29 | 4.24 64 | 5.45 60 | 18.3 87 | 3.32 34 | 5.20 90 | 28.1 115 | 2.00 7 | 9.49 63 | 16.4 78 | 1.91 18 |
Aniso-Texture [82] | 59.0 | 3.11 2 | 6.78 32 | 1.73 2 | 5.45 88 | 10.3 111 | 1.73 1 | 4.08 94 | 7.00 47 | 1.41 1 | 6.56 58 | 9.47 91 | 4.32 86 | 12.2 102 | 16.4 85 | 4.24 64 | 5.80 108 | 20.7 124 | 3.32 34 | 4.97 10 | 24.9 64 | 2.00 7 | 9.75 93 | 16.7 95 | 1.91 18 |
HBpMotionGpu [43] | 59.5 | 3.42 108 | 6.98 50 | 1.91 117 | 6.19 116 | 10.7 122 | 2.08 116 | 4.00 11 | 6.68 15 | 1.41 1 | 6.78 95 | 9.95 104 | 4.36 101 | 12.0 31 | 16.1 29 | 4.20 10 | 5.57 90 | 17.7 65 | 3.32 34 | 5.00 40 | 23.8 27 | 2.00 7 | 9.52 68 | 16.1 53 | 1.91 18 |
GraphCuts [14] | 61.8 | 3.37 96 | 7.53 100 | 1.73 2 | 5.03 62 | 8.39 41 | 1.83 93 | 4.36 105 | 6.68 15 | 1.41 1 | 6.83 98 | 9.56 94 | 4.32 86 | 12.1 70 | 16.3 64 | 4.16 2 | 5.26 13 | 17.5 61 | 3.16 1 | 5.03 56 | 25.6 81 | 2.08 98 | 9.95 113 | 17.1 112 | 1.91 18 |
Ad-TV-NDC [36] | 63.0 | 3.65 117 | 6.68 17 | 2.00 122 | 6.16 114 | 10.2 107 | 2.08 116 | 4.00 11 | 7.35 82 | 1.41 1 | 6.98 102 | 9.47 91 | 4.43 107 | 12.1 70 | 16.1 29 | 4.24 64 | 5.32 25 | 16.3 16 | 3.42 118 | 5.20 90 | 24.3 43 | 2.00 7 | 9.42 35 | 15.5 9 | 1.91 18 |
Black & Anandan [4] | 63.3 | 3.37 96 | 6.68 17 | 1.83 104 | 6.06 113 | 10.4 115 | 1.83 93 | 4.36 105 | 7.72 105 | 1.41 1 | 7.07 109 | 9.90 103 | 4.24 1 | 12.1 70 | 16.1 29 | 4.24 64 | 5.26 13 | 16.9 33 | 3.32 34 | 5.32 105 | 26.4 98 | 2.00 7 | 9.49 63 | 15.8 24 | 1.91 18 |
Shiralkar [42] | 65.2 | 3.32 78 | 7.96 115 | 1.73 2 | 5.60 98 | 9.85 100 | 1.73 1 | 4.00 11 | 8.43 118 | 1.41 1 | 7.12 110 | 11.1 117 | 4.24 1 | 12.0 31 | 16.3 64 | 4.16 2 | 5.57 90 | 18.3 87 | 3.37 103 | 5.35 110 | 29.8 124 | 2.00 7 | 9.56 72 | 17.0 106 | 1.91 18 |
FlowNet2 [122] | 67.7 | 3.70 118 | 10.2 125 | 1.83 104 | 5.20 75 | 9.00 68 | 1.83 93 | 4.08 94 | 7.68 100 | 1.41 1 | 6.76 93 | 11.0 115 | 4.24 1 | 12.2 102 | 16.6 109 | 4.24 64 | 5.35 40 | 17.3 55 | 3.27 17 | 5.03 56 | 25.8 86 | 2.00 7 | 9.42 35 | 16.3 65 | 1.83 1 |
Filter Flow [19] | 68.1 | 3.37 96 | 6.93 47 | 1.83 104 | 5.80 107 | 9.98 103 | 2.08 116 | 4.00 11 | 7.05 64 | 1.41 1 | 6.95 101 | 9.09 63 | 4.43 107 | 12.2 102 | 16.3 64 | 4.24 64 | 5.35 40 | 17.4 57 | 3.32 34 | 5.10 77 | 25.3 73 | 2.00 7 | 9.83 101 | 16.4 78 | 1.91 18 |
Bartels [41] | 68.8 | 3.32 78 | 7.35 85 | 1.73 2 | 5.03 62 | 9.26 76 | 1.83 93 | 4.00 11 | 7.00 47 | 1.41 1 | 6.73 92 | 9.42 83 | 4.69 123 | 12.0 31 | 15.9 8 | 4.55 129 | 5.94 120 | 18.4 93 | 3.87 130 | 5.03 56 | 23.2 9 | 2.08 98 | 9.47 53 | 16.0 43 | 2.00 128 |
AdaConv-v1 [126] | 69.7 | 3.70 118 | 9.42 123 | 1.91 117 | 5.92 110 | 9.04 71 | 2.38 126 | 4.36 105 | 7.68 100 | 1.73 120 | 8.52 126 | 13.0 126 | 4.62 118 | 11.4 1 | 15.2 1 | 4.08 1 | 4.90 2 | 15.0 2 | 3.16 1 | 4.97 10 | 24.0 34 | 2.16 128 | 8.98 2 | 15.0 2 | 2.00 128 |
IAOF2 [51] | 71.5 | 3.46 112 | 7.59 106 | 1.73 2 | 5.74 106 | 10.9 126 | 1.83 93 | 3.70 2 | 7.14 77 | 1.41 1 | 6.98 102 | 10.0 106 | 4.32 86 | 12.3 116 | 16.8 119 | 4.20 10 | 5.51 86 | 18.6 99 | 3.32 34 | 5.10 77 | 25.3 73 | 2.00 7 | 9.75 93 | 16.3 65 | 1.91 18 |
LocallyOriented [52] | 71.7 | 3.37 96 | 7.42 93 | 1.73 2 | 5.80 107 | 10.6 120 | 1.73 1 | 4.00 11 | 7.68 100 | 1.41 1 | 6.81 97 | 10.1 107 | 4.32 86 | 12.1 70 | 16.4 85 | 4.20 10 | 5.80 108 | 18.3 87 | 3.42 118 | 5.32 105 | 26.6 99 | 2.00 7 | 9.81 97 | 16.7 95 | 1.91 18 |
ROF-ND [107] | 72.2 | 3.46 112 | 6.98 50 | 1.73 2 | 5.10 72 | 9.42 78 | 1.73 1 | 4.08 94 | 7.12 75 | 1.41 1 | 7.16 112 | 11.7 124 | 4.24 1 | 12.1 70 | 16.3 64 | 4.24 64 | 5.80 108 | 20.0 119 | 3.27 17 | 5.57 122 | 26.7 104 | 2.08 98 | 9.95 113 | 17.3 115 | 1.91 18 |
TriangleFlow [30] | 72.5 | 3.37 96 | 7.70 109 | 1.73 2 | 5.35 81 | 9.70 91 | 1.73 1 | 4.08 94 | 7.19 79 | 1.41 1 | 6.78 95 | 10.1 107 | 4.32 86 | 12.0 31 | 16.2 46 | 4.16 2 | 5.77 107 | 18.6 99 | 3.32 34 | 5.32 105 | 29.0 118 | 2.08 98 | 10.1 118 | 17.8 121 | 1.91 18 |
Correlation Flow [75] | 72.6 | 3.16 59 | 7.70 109 | 1.73 2 | 5.35 81 | 10.1 105 | 1.73 1 | 4.00 11 | 6.68 15 | 1.41 1 | 6.61 83 | 9.20 74 | 4.40 105 | 12.1 70 | 16.3 64 | 4.40 127 | 6.06 126 | 20.6 123 | 3.32 34 | 5.35 110 | 29.5 122 | 2.08 98 | 9.88 106 | 16.8 98 | 1.91 18 |
SegOF [10] | 73.3 | 3.11 2 | 7.07 62 | 1.83 104 | 5.35 81 | 9.20 75 | 1.83 93 | 4.36 105 | 8.00 110 | 1.41 1 | 6.98 102 | 11.3 119 | 4.24 1 | 12.1 70 | 16.3 64 | 4.24 64 | 5.72 99 | 18.1 83 | 3.32 34 | 5.26 103 | 29.4 121 | 2.08 98 | 9.47 53 | 16.8 98 | 1.91 18 |
Dynamic MRF [7] | 74.0 | 3.11 2 | 7.44 96 | 1.73 2 | 5.20 75 | 9.80 96 | 1.73 1 | 4.36 105 | 8.68 119 | 1.41 1 | 7.33 116 | 10.7 113 | 4.55 114 | 12.1 70 | 16.4 85 | 4.20 10 | 5.80 108 | 20.4 122 | 3.37 103 | 5.29 104 | 29.0 118 | 2.00 7 | 9.83 101 | 16.5 89 | 1.91 18 |
SPSA-learn [13] | 75.7 | 3.32 78 | 6.73 27 | 1.73 2 | 5.66 101 | 9.59 83 | 1.83 93 | 4.36 105 | 7.35 82 | 1.41 1 | 7.05 107 | 9.57 96 | 4.24 1 | 12.1 70 | 16.6 109 | 4.24 64 | 5.45 60 | 18.0 77 | 3.32 34 | 5.66 126 | 35.7 131 | 2.08 98 | 10.4 124 | 20.9 129 | 1.91 18 |
Horn & Schunck [3] | 77.5 | 3.42 108 | 7.14 69 | 1.83 104 | 6.27 117 | 10.6 120 | 1.91 108 | 4.36 105 | 8.35 114 | 1.41 1 | 7.70 121 | 11.0 115 | 4.24 1 | 12.1 70 | 16.2 46 | 4.24 64 | 5.35 40 | 16.7 29 | 3.32 34 | 5.60 123 | 27.3 109 | 2.08 98 | 9.75 93 | 16.1 53 | 1.91 18 |
TI-DOFE [24] | 80.6 | 3.70 118 | 7.51 99 | 2.16 125 | 6.95 126 | 11.1 128 | 2.16 120 | 4.36 105 | 8.35 114 | 1.41 1 | 7.72 122 | 10.9 114 | 4.36 101 | 12.0 31 | 16.2 46 | 4.20 10 | 5.35 40 | 16.9 33 | 3.32 34 | 5.45 115 | 25.3 73 | 2.08 98 | 9.93 111 | 16.1 53 | 1.91 18 |
StereoOF-V1MT [119] | 80.6 | 3.37 96 | 8.12 116 | 1.73 2 | 5.48 92 | 9.71 92 | 1.73 1 | 4.36 105 | 8.35 114 | 1.41 1 | 7.53 120 | 11.1 117 | 4.51 111 | 12.2 102 | 16.6 109 | 4.20 10 | 5.94 120 | 18.0 77 | 3.37 103 | 5.60 123 | 27.6 112 | 2.08 98 | 9.47 53 | 16.0 43 | 1.91 18 |
StereoFlow [44] | 81.6 | 5.20 131 | 12.2 131 | 2.00 122 | 6.98 127 | 11.2 129 | 2.16 120 | 4.00 11 | 7.35 82 | 1.41 1 | 6.56 58 | 8.83 46 | 4.24 1 | 14.1 130 | 20.1 130 | 4.24 64 | 7.05 131 | 24.6 131 | 3.32 34 | 5.03 56 | 24.8 59 | 2.00 7 | 10.2 119 | 17.7 120 | 1.91 18 |
ACK-Prior [27] | 82.2 | 3.11 2 | 7.55 104 | 1.73 2 | 4.97 51 | 8.70 55 | 1.73 1 | 4.36 105 | 7.35 82 | 1.41 1 | 6.86 100 | 10.1 107 | 4.32 86 | 12.4 119 | 16.8 119 | 4.32 122 | 6.03 124 | 20.3 121 | 3.37 103 | 5.23 100 | 26.8 105 | 2.08 98 | 10.7 127 | 18.1 122 | 1.91 18 |
UnFlow [129] | 85.5 | 3.56 115 | 9.26 122 | 1.83 104 | 6.00 112 | 9.87 101 | 1.83 93 | 4.36 105 | 8.68 119 | 1.41 1 | 6.76 93 | 10.2 110 | 4.24 1 | 12.2 102 | 16.7 114 | 4.24 64 | 5.92 119 | 20.0 119 | 3.32 34 | 5.35 110 | 24.1 38 | 2.00 7 | 10.7 127 | 18.3 125 | 1.91 18 |
2bit-BM-tele [98] | 86.5 | 3.37 96 | 6.68 17 | 1.83 104 | 5.48 92 | 10.1 105 | 1.91 108 | 4.00 11 | 6.78 43 | 1.41 1 | 6.68 87 | 9.11 67 | 4.69 123 | 12.2 102 | 16.4 85 | 4.43 128 | 5.83 117 | 21.0 127 | 3.70 128 | 5.45 115 | 35.2 130 | 2.16 128 | 9.31 22 | 15.6 11 | 2.08 130 |
NL-TV-NCC [25] | 89.8 | 3.46 112 | 8.50 119 | 1.73 2 | 5.26 77 | 9.83 99 | 1.73 1 | 4.36 105 | 7.68 100 | 1.41 1 | 7.39 119 | 11.6 123 | 4.55 114 | 12.2 102 | 16.3 64 | 4.55 129 | 6.19 128 | 19.6 115 | 3.32 34 | 6.76 131 | 28.0 113 | 2.16 128 | 10.2 119 | 16.9 103 | 1.91 18 |
Learning Flow [11] | 91.4 | 3.42 108 | 7.59 106 | 1.73 2 | 5.72 104 | 10.3 111 | 1.73 1 | 4.51 121 | 8.68 119 | 1.41 1 | 7.26 114 | 9.85 101 | 4.55 114 | 12.4 119 | 16.7 114 | 4.36 124 | 5.66 96 | 18.1 83 | 3.37 103 | 5.45 115 | 26.6 99 | 2.08 98 | 10.2 119 | 16.9 103 | 1.91 18 |
SILK [79] | 99.8 | 3.56 115 | 8.12 116 | 1.91 117 | 6.61 124 | 10.8 124 | 2.08 116 | 4.69 122 | 8.68 119 | 1.73 120 | 7.35 117 | 10.4 112 | 4.65 119 | 12.2 102 | 16.4 85 | 4.24 64 | 5.72 99 | 17.7 65 | 3.56 127 | 5.32 105 | 24.6 56 | 2.08 98 | 9.68 89 | 16.3 65 | 1.91 18 |
Adaptive flow [45] | 104.2 | 4.04 124 | 7.72 111 | 2.16 125 | 6.98 127 | 10.8 124 | 2.52 129 | 4.24 104 | 7.35 82 | 1.63 119 | 7.26 114 | 9.56 94 | 4.69 123 | 12.4 119 | 16.8 119 | 4.24 64 | 5.80 108 | 20.7 124 | 3.37 103 | 5.20 90 | 25.0 66 | 2.08 98 | 9.90 109 | 17.0 106 | 1.91 18 |
SLK [47] | 104.8 | 3.70 118 | 8.76 121 | 2.08 124 | 6.35 118 | 9.59 83 | 2.16 120 | 4.93 125 | 8.68 119 | 1.73 120 | 8.70 128 | 13.3 128 | 4.69 123 | 12.5 123 | 17.1 126 | 4.16 2 | 5.97 122 | 18.4 93 | 3.32 34 | 5.74 128 | 29.2 120 | 2.08 98 | 9.93 111 | 17.2 114 | 1.91 18 |
FOLKI [16] | 106.5 | 4.08 125 | 8.29 118 | 2.45 129 | 7.05 129 | 10.7 122 | 2.38 126 | 4.69 122 | 9.35 126 | 1.73 120 | 8.60 127 | 11.5 120 | 5.10 129 | 12.4 119 | 16.7 114 | 4.24 64 | 5.69 97 | 17.1 45 | 3.42 118 | 5.48 119 | 25.8 86 | 2.08 98 | 9.88 106 | 16.4 78 | 1.91 18 |
GroupFlow [9] | 107.4 | 3.74 123 | 11.0 129 | 1.91 117 | 5.92 110 | 10.3 111 | 1.91 108 | 4.76 124 | 9.98 128 | 1.73 120 | 7.35 117 | 13.0 126 | 4.32 86 | 12.9 128 | 18.2 128 | 4.24 64 | 6.06 126 | 21.7 129 | 3.37 103 | 5.42 114 | 31.0 127 | 2.00 7 | 10.4 124 | 19.6 127 | 1.83 1 |
FFV1MT [106] | 110.0 | 3.70 118 | 10.3 127 | 1.83 104 | 6.40 120 | 9.66 87 | 2.16 120 | 5.69 128 | 12.0 130 | 1.73 120 | 8.19 124 | 11.5 120 | 4.65 119 | 12.5 123 | 16.8 119 | 4.24 64 | 5.89 118 | 17.5 61 | 3.42 118 | 5.83 129 | 30.0 125 | 2.08 98 | 10.4 124 | 18.4 126 | 1.91 18 |
Heeger++ [104] | 112.0 | 4.08 125 | 11.4 130 | 1.83 104 | 6.38 119 | 9.80 96 | 1.91 108 | 5.69 128 | 11.0 129 | 1.73 120 | 8.19 124 | 11.5 120 | 4.65 119 | 12.8 127 | 17.7 127 | 4.24 64 | 6.24 129 | 18.6 99 | 3.37 103 | 6.03 130 | 30.7 126 | 2.08 98 | 10.3 123 | 18.1 122 | 1.91 18 |
PGAM+LK [55] | 112.5 | 4.08 125 | 9.76 124 | 2.16 125 | 6.40 120 | 10.4 115 | 2.16 120 | 5.00 126 | 9.81 127 | 1.73 120 | 8.70 128 | 13.4 129 | 5.10 129 | 12.5 123 | 16.8 119 | 4.24 64 | 6.03 124 | 19.4 114 | 3.51 125 | 5.45 115 | 26.2 94 | 2.08 98 | 9.95 113 | 17.0 106 | 1.91 18 |
HCIC-L [99] | 114.0 | 4.55 130 | 10.7 128 | 2.65 131 | 6.40 120 | 10.2 107 | 2.45 128 | 5.00 126 | 8.68 119 | 1.73 120 | 8.12 123 | 12.3 125 | 4.51 111 | 12.6 126 | 17.0 125 | 4.36 124 | 5.97 122 | 21.1 128 | 3.37 103 | 5.10 77 | 25.8 86 | 2.08 98 | 11.8 131 | 21.2 130 | 1.91 18 |
Pyramid LK [2] | 114.1 | 4.08 125 | 8.68 120 | 2.58 130 | 7.75 130 | 11.0 127 | 2.71 130 | 7.00 130 | 8.00 110 | 2.00 130 | 13.9 131 | 26.4 131 | 5.60 131 | 13.5 129 | 20.0 129 | 4.24 64 | 5.72 99 | 17.9 72 | 3.37 103 | 5.48 119 | 29.7 123 | 2.08 98 | 11.6 129 | 23.4 131 | 1.91 18 |
Periodicity [78] | 129.3 | 4.32 129 | 10.2 125 | 2.38 128 | 9.88 131 | 11.9 131 | 3.00 131 | 7.35 131 | 14.4 131 | 2.38 131 | 9.56 130 | 24.6 130 | 4.97 128 | 14.3 131 | 20.9 131 | 4.55 129 | 6.38 130 | 21.9 130 | 3.87 130 | 5.51 121 | 33.0 129 | 2.16 128 | 11.6 129 | 19.9 128 | 2.16 131 |
Method | time* | frames | color | Reference and notes | |
[1] 2D-CLG | 844 | 2 | gray | The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences. | |
[2] Pyramid LK | 12 | 2 | color | A modification of Bouguet's pyramidal implementation of Lucas-Kanade. | |
[3] Horn & Schunck | 49 | 2 | gray | A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data. | |
[4] Black & Anandan | 328 | 2 | gray | A modern Matlab implementation of the Black & Anandan method by Deqing Sun. | |
[5] Brox et al. | 18 | 2 | color | T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.) | |
[6] Fusion | 2,666 | 2 | color | V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008. | |
[7] Dynamic MRF | 366 | 2 | gray | B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.) | |
[8] Second-order prior | 14 | 2 | gray | W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[9] GroupFlow | 600 | 2 | gray | X. Ren. Local Grouping for Optical Flow. CVPR 2008. | |
[10] SegOF | 60 | 2 | color | L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available. | |
[11] Learning Flow | 825 | 2 | gray | D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008. | |
[12] CBF | 69 | 2 | color | W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.) | |
[13] SPSA-learn | 200 | 2 | color | Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008. | |
[14] GraphCuts | 1,200 | 2 | color | T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008. | |
[15] F-TV-L1 | 8 | 2 | gray | A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008. | |
[16] FOLKI | 1.4 | 2 | gray | G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005. | |
[17] TV-L1-improved | 2.9 | 2 | gray | A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision. | |
[18] DPOF | 287 | 2 | color | C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.) | |
[19] Filter Flow | 34,000 | 2 | color | S. Seitz and S. Baker. Filter flow. ICCV 2009. | |
[20] Adaptive | 9.2 | 2 | gray | A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009. | |
[21] Complementary OF | 44 | 2 | color | H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009. | |
[22] Aniso. Huber-L1 | 2 | 2 | gray | M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision. | |
[23] Rannacher | 0.12 | 2 | gray | J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009. | |
[24] TI-DOFE | 260 | 2 | gray | C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009. | |
[25] NL-TV-NCC | 20 | 2 | color | M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010. | |
[26] MDP-Flow | 188 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010. | |
[27] ACK-Prior | 5872 | 2 | color | K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010. | |
[28] LDOF | 122 | 2 | color | T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011. | |
[29] p-harmonic | 565 | 2 | gray | J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010. | |
[30] TriangleFlow | 4200 | 2 | gray | B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010. | |
[31] Classic+NL | 972 | 2 | color | D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code. | |
[32] Classic++ | 486 | 2 | gray | A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010. | |
[33] Nguyen | 33 | 2 | gray | D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011. | |
[34] Modified CLG | 133 | 2 | gray | R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010. | |
[35] ComplOF-FED-GPU | 0.97 | 2 | color | P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010. | |
[36] Ad-TV-NDC | 35 | 2 | gray | M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010. | |
[37] Layers++ | 18206 | 2 | color | D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010. | |
[38] OFH | 620 | 3 | color | H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011. | |
[39] LSM | 1615 | 2 | color | K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011. | |
[40] CostFilter | 55 | 2 | color | C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011. | |
[41] Bartels | 0.15 | 2 | gray | C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU. | |
[42] Shiralkar | 600 | 2 | gray | M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242. | |
[43] HBpMotionGpu | 1000 | 5 | gray | S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.) | |
[44] StereoFlow | 7200 | 2 | color | G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772. | |
[45] Adaptive flow | 121 | 2 | gray | T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011. | |
[46] TC-Flow | 2500 | 5 | color | S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011. | |
[47] SLK | 300 | 2 | gray | T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011. | |
[48] CLG-TV | 29 | 2 | gray | M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code. | |
[49] SimpleFlow | 1.7 | 2 | color | M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012. | |
[50] IAOF | 57 | 2 | gray | D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011. | |
[51] IAOF2 | 56 | 2 | gray | D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011. | |
[52] LocallyOriented | 9541 | 2 | gray | Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012. | |
[53] IROF-TV | 261 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop. | |
[54] Sparse Occlusion | 2312 | 2 | color | A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011. | |
[55] PGAM+LK | 0.37 | 2 | gray | A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010. | |
[56] Sparse-NonSparse | 713 | 2 | color | L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013. | |
[57] nLayers | 36150 | 4 | color | D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012. | |
[58] IROF++ | 187 | 2 | color | H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013. | |
[59] COFM | 600 | 3 | color | M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013. | |
[60] Efficient-NL | 400 | 2 | color | P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012. | |
[61] BlockOverlap | 2 | 2 | gray | M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012. | |
[62] Ramp | 1200 | 2 | color | A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012. | |
[63] Occlusion-TV-L1 | 538 | 3 | gray | C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012. | |
[64] TV-L1-MCT | 90 | 2 | color | M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012. | |
[65] Local-TV-L1 | 500 | 2 | gray | L. Raket. Local smoothness for global optical flow. ICIP 2012. | |
[66] ALD-Flow | 61 | 2 | color | M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012. | |
[67] SIOF | 234 | 2 | color | L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012. | |
[68] MDP-Flow2 | 342 | 2 | color | L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available. | |
[69] TCOF | 1421 | all | gray | J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013. | |
[70] LME | 476 | 2 | color | W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013. | |
[71] NN-field | 362 | 2 | color | L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013. | |
[72] FESL | 3310 | 2 | color | W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013. | |
[73] PMF | 35 | 2 | color | J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013. | |
[74] FC-2Layers-FF | 2662 | 4 | color | D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013. | |
[75] Correlation Flow | 290 | 2 | color | M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code. | |
[76] TC/T-Flow | 341 | 5 | color | M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013. | |
[77] OFLAF | 1530 | 2 | color | T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013. | |
[78] Periodicity | 8000 | 4 | color | G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013. | |
[79] SILK | 572 | 2 | gray | P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP. | |
[80] CRTflow | 13 | 3 | color | O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013. | |
[81] SuperFlow | 178 | 2 | color | Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507. | |
[82] Aniso-Texture | 300 | 2 | color | Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267. | |
[83] Classic+CPF | 640 | 2 | gray | Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013. | |
[84] S2D-Matching | 1200 | 2 | color | Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479. | |
[85] AGIF+OF | 438 | 2 | gray | Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015. | |
[86] DeepFlow | 13 | 2 | color | P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013. | |
[87] NNF-Local | 673 | 2 | color | Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014. | |
[88] EPPM w/o HM | 2.5 | 2 | color | L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014. | |
[89] MLDP_OF | 165 | 2 | gray | M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014. | |
[90] RFlow | 20 | 2 | gray | S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014. | |
[91] SRR-TVOF-NL | 32 | all | color | P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014. | |
[92] 2DHMM-SAS | 157 | 2 | color | M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission. | |
[93] WLIF-Flow | 700 | 2 | color | Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014. | |
[94] FMOF | 215 | 2 | color | N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014. | |
[95] TriFlow | 150 | 2 | color | TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914. | |
[96] ComponentFusion | 6.5 | 2 | color | Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941. | |
[97] AggregFlow | 1642 | 2 | color | D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759. | |
[98] 2bit-BM-tele | 124 | 2 | gray | R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013. | |
[99] HCIC-L | 330 | 2 | color | Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114. | |
[100] TF+OM | 600 | 2 | color | R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015. | |
[101] PH-Flow | 800 | 2 | color | J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015. | |
[102] EpicFlow | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015. | |
[103] NNF-EAC | 380 | 2 | color | Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336. | |
[104] Heeger++ | 6600 | 5 | gray | Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238. | |
[105] HBM-GC | 330 | 2 | color | A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015. | |
[106] FFV1MT | 358 | 5 | gray | F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015. | |
[107] ROF-ND | 4 | 2 | color | S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015. | |
[108] DeepFlow2 | 16 | 2 | color | J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015. | |
[109] HAST | 2667 | 2 | color | Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221. | |
[110] FlowFields | 15 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015. | |
[111] SVFilterOh | 1.56 | 2 | color | Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788. | |
[112] FlowNetS+ft+v | 0.5 | 2 | color | Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235. | |
[113] CombBMOF | 51 | 2 | color | M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.) | |
[114] PMMST | 182 | 2 | color | F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015. | |
[115] DF-Auto | 70 | 2 | color | N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015. | |
[116] CPM-Flow | 3 | 2 | color | Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241. | |
[117] CNN-flow-warp+ref | 1.4 | 3 | color | D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016. | |
[118] Steered-L1 | 804 | 2 | color | Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016. | |
[119] StereoOF-V1MT | 343 | 2 | gray | Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132. | |
[120] PGM-C | 5 | 2 | color | Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016. | |
[121] RNLOD-Flow | 1040 | 2 | gray | C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. Submitted to TIP 2016. | |
[122] FlowNet2 | 0.091 | 2 | color | Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900. | |
[123] S2F-IF | 20 | 2 | color | Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765. | |
[124] BriefMatch | 0.068 | 2 | gray | G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62. | |
[125] OAR-Flow | 60 | 2 | color | Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20. | |
[126] AdaConv-v1 | 2.8 | 2 | color | S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017. | |
[127] SepConv-v1 | 0.2 | 2 | color | S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017. | |
[128] ProbFlowFields | 37 | 2 | color | A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017. | |
[129] UnFlow | 0.12 | 2 | color | Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018. | |
[130] FlowFields+ | 10.5 | 2 | color | C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017. | |
[131] Kuang | 9.9 | 2 | gray | F. Kuang. PatchMatch algorithms for motion estimation and stereo reconstruction. Master thesis, University of Stuttgart, 2017. |